CN101471845B - Method for adjusting data block counterpart number and metadata server node - Google Patents
Method for adjusting data block counterpart number and metadata server node Download PDFInfo
- Publication number
- CN101471845B CN101471845B CN2007103047141A CN200710304714A CN101471845B CN 101471845 B CN101471845 B CN 101471845B CN 2007103047141 A CN2007103047141 A CN 2007103047141A CN 200710304714 A CN200710304714 A CN 200710304714A CN 101471845 B CN101471845 B CN 101471845B
- Authority
- CN
- China
- Prior art keywords
- copy
- data block
- node
- adjustment information
- adjustment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Abstract
The invention relates to a method for regulating the number of duplicate data blocks and a meta-data server node. The method comprises the following steps: searching a duplicate regulation message of a duplicate data block by a meta-data server node; and regulating the number of duplicate data blocks stored in a data block node when a duplicate regulation time point set in the duplicate regulation message arrives at according to duplicate regulation number in the duplicate regulation message corresponding to the duplicate regulation time point. The meta-data server node comprises a meta-data processing module and a duplicate management module. The invention can set higher number of duplicate for the data block with long response time or high access frequency, so as to increase the aggregated bandwidth for a user accessing the data, thereby ensuring the availability and the reliability of the data block while improving the utilization efficiency of system resources.
Description
Technical field
The present invention relates to a kind of adjustment technology of data block copy amount, relate in particular to the method for adjustment and the corresponding metadata server node of the data block copy amount in the distributed file system.
Background technology
Distributed file system is a kind of distributed memory system that local storage makes up based on cheap computer node.It is built into a directory tree by the Shared Folders on the different server is organized together, and making the user only need visit a shared root is the addressable file or folder that is distributed on the network, and needn't know the actual physical location of these files.(Storage Area Network, be called for short: SAN) storage system is compared, and advantages such as storage cost performance height, extensibility are strong are arranged with traditional disk array and storage area network.
The existing distributed file system can also be by Internet service provider, as Google, Yahoo etc., as data processing platform (DPP).As shown in Figure 1, the existing distributed file system is made up of metadata server node and a plurality of data block node usually.Wherein, metadata server node is used to preserve the title of data block node at deblocking situation, each data block place of each file, and the information of the data block that comprises on each data block node etc.; The data block node is used to preserve actual data block, and each data block size is 64MB or 128MB usually.When client software need carry out the data access visit to above-mentioned distributed file system, at first obtain or set up the position of the data block of file by metadata server node; Data block node direct then and the respective data blocks place communicates, and operations such as piece read and write data.
The existing distributed file system is general to adopt common cheap computer node as hardware platform, because common computer node reliability is not high, in order to improve system reliability and availability of data, distributed file system adopts many copies mode of fixed qty to preserve data block usually, for example, can preserve 3 copies at different data block nodes for same data block.Metadata server node is by the state of each data block node of heartbeat monitor, each data block always has fixing number of copies in the assurance system, so that when certain computer node is delayed machine, still available data trnascription can be arranged, to guarantee the reliability of system.
The defective of prior art is: many copies mode of above-mentioned distributed file system has only been considered the availability of data and has not been considered response time of different pieces of information in the telecommunication service and access frequency different.For different data, the migration along with the time of its access frequency and response time changes.When the access frequency of some data raise, the required aggregate bandwidth of each data block increased.Yet, because the number of copies of in the existing distributed file system each data block being set is all fixed, therefore be difficult to satisfy the needs of high access frequency, increased the response time of respective data blocks, influenced the raising of system applies performance.
Summary of the invention
The problem to be solved in the present invention is: adopt the fixedly distributed file system of copy amount, can't adjust copy amount according to the access frequency or the response time of data block, thereby influence the raising of systematic function.
In order to address the above problem, one embodiment of the present of invention have provided a kind of data block copy amount regulation method, comprising:
Metadata server node is inquired about the copy adjustment information of a data block copy;
When the copy adjustment of setting in the described copy adjustment information reaches constantly, according to the constantly corresponding copy adjustment of this copy adjustment is several the copy amount that is kept at the described data block copy in the data block node being adjusted in the described copy adjustment information.
In order to address the above problem, one embodiment of the present of invention have provided a kind of metadata server node, comprise metadata processing module and replica management module, wherein:
The metadata processing module comprises first processing sub, be used to inquire about the copy adjustment information of a data block copy, when the copy adjustment of setting in the described copy adjustment information reaches constantly, according to adjusting number with the constantly corresponding copy of this copy adjustment in the described copy adjustment information, send copy adjustment instruction to the replica management module;
The replica management module comprises the first management submodule, is used for select the preservation position of the data block copy of respective numbers, and data block copy being saved in the corresponding data block node according to the copy adjustment instruction that comes from first processing sub.
By the present invention, metadata server node can be adjusted according to the copy adjustment moment that comprises in the copy adjustment information and the several copy amounts to each data block of copy adjustment.Make and more copy amount to be set data block very long to the response time or that access frequency is high, to improve the aggregate bandwidth of these data of user capture; And, shorten when the response time of data block, or access frequency reduces number of copies, so that leave memory space and input output band width for other data block when descending.Thereby in the availability and reliability that guarantee data block, improved the utilization ratio of system resource.
Below by drawings and Examples, technical scheme of the present invention is described in further detail.
Description of drawings
Fig. 1 is an existing distributed file system structure schematic diagram;
Fig. 2 is the flow chart of data block copy amount regulation method embodiment 1 of the present invention;
Fig. 3 is the flow chart of data block copy amount regulation method embodiment 2 of the present invention;
The structural representation of Fig. 4 metadata server node embodiment 1 of the present invention;
The structural representation of Fig. 5 metadata server node embodiment 2 of the present invention;
The structural representation of Fig. 6 metadata server node embodiment 3 of the present invention.
Embodiment
Method embodiment 1
Present embodiment provides a kind of distributed file system data block copy amount regulation method, as shown in Figure 2, comprising:
After step 101, the metadata server node in the distributed file system receive the copy adjustment information that comes from user side, this copy adjustment information is kept in this metadata server node.
Wherein, comprise in this copy adjustment information at the copy adjustment of certain data block copy and adjust number constantly and with the constantly corresponding copy of this copy adjustment.In addition, the copy adjustment information can also comprise other useful informations as required, as document misregistration amount etc.
Particularly, can set a plurality of copy adjustment moment and copy adjustment number at a data block copy in this copy adjustment information, wherein each copy adjustment number average is constantly corresponding with a copy adjustment.For example, as shown in table 1, data block D1 is at T
10 creates constantly, and keeping number of copies during establishment is R
10, this number of copies remains to T always
11 constantly; At T
1The number of copies of 1 moment data block D1 is put in order is R
11, at T
12 are adjusted to R constantly
12.Similarly, data block D2 is at T
20 creates constantly, and keeping number of copies during establishment is R
20, this number of copies remains to T always
21 constantly; At T
2The number of copies of 1 moment data block D2 is put in order is R
21.
Table 1
| Data block | Adjust constantly | Number of copies |
| D1 | T 10 | R 10 |
| D1 | T 11 | R 11 |
| D1 | T 12 | R 12 |
| D2 | T 20 | R 20 |
| D2 | T 21 | R 21 |
| … | … | … |
It needs to be noted that herein this step is to be set the copy adjustment information of certain data block copy by client.In addition, alternatively, also the copy adjustment information that is kept at data block copy in the data block node at all can be kept in advance in the metadata server node, in this copy adjustment information, also be set with the copy adjustment and adjust number with copy correspondingly constantly.For example, can preestablish any data block copy when creating, have R1 data block copy in preceding Day1 days, had R2 data block copy in ensuing Day2 days, the rest may be inferred.
In addition, the above-mentioned dual mode that is set by the user copy adjustment information and default copy adjustment information also can be used in combination.Promptly earlier default copy adjustment information, when the user sets copy adjustment information at certain data block copy, again with the copy adjustment information set instead of at the original default copy adjustment information of certain data block.And no matter adopt above-mentioned which kind of scheme ghost adjustment information, user side can upgrade copy adjustment information wherein by the visit distributed file system at any time.Particularly, user side can be adjusted number to the moment of the copy adjustment in the copy adjustment information, copy and upgrade accordingly as required.Thereby make user side to adjust the copy amount of data block copy, improved the controllability of system, satisfied user's demand according to the needs of oneself.
Step 102, the copy adjustment information of metadata server node data query piece copy, when the copy adjustment of setting in this copy adjustment information reaches constantly, adjust according to adjusting several copy amounts with the constantly corresponding copy of this copy adjustment in the copy adjustment information to this data block copy.
Concrete adjustment process comprises: according to adjusting the data block address of node that number is selected respective numbers corresponding to this copy adjustment copy constantly in the copy adjustment information; Data block copy with respective numbers is saved in the corresponding data block node then.
Step 103, when metadata server node adjust according to the copy in the copy adjustment information several copy amounts to data block copy finish once adjust after, can also carry out heartbeat monitor to the state of the data block node of preserving above-mentioned data block copy.
Particularly, in carrying out the heartbeat monitor process, if monitor when wherein certain data block node is unavailable, for example can't carry out operate as normal, then adjust several copy amounts according to the copy in the above-mentioned copy adjustment information once more and adjust the respective data blocks copy owing to reasons such as the machine of delaying make this data block node.Need to prove herein, if since this data block node unavailable and have influence on the data block copy amount of certain data block copy then need the copy amount of this data block copy is adjusted; Otherwise can it not adjusted, because copy amount is not affected yet.By the data block node is carried out heartbeat monitor, can be when the data block node be unavailable, the number of copies of setting in the copy amount of data block copy and the copy adjustment information is consistent, thereby can further improves the reliability of system.
Step 104, if set a plurality of copy adjustment constantly and copy correspondingly when adjusting number at certain data block copy in the copy adjustment information, then when next copy adjustment arrives constantly, metadata server node still can be according to the described method of step 102, according to adjusting number corresponding to this copy adjustment copy constantly in the copy adjustment information, the copy amount of data block copy is adjusted once more.
By the described method of present embodiment, metadata server node can be adjusted several copy amounts to each data block copy with copy correspondingly constantly according to the copy adjustment that comprises in the copy adjustment information and adjust.Make and more copy amount to be set data block copy very long to the response time or that access frequency is high, to improve the aggregate bandwidth of these data of user capture; And, shorten when the response time of data block copy, or access frequency reduces copy amount, so that leave memory space and input output band width for other data block copy when descending.Thereby in the availability and reliability that guarantee data block copy, improved the utilization ratio of system resource.
In method embodiment 1 described method, after having created data block copy in the data block node, set according to user side, perhaps copy data is adjusted according to the copy adjustment information that in metadata server node, prestores.Present embodiment provides a kind of user side when creating data block copy, sets the copy amount regulation method of copy adjustment information, as shown in Figure 3, comprising:
Wherein, this data block is created the copy adjustment information that includes in the instruction at data block copy to be created.Comprise the copy adjustment moment in this copy adjustment information and adjust number with the constantly corresponding copy of this copy adjustment.
In addition, data block is created all right include file side-play amount in the instruction.The document misregistration amount be meant with the data block corresponding file in the position, for example a file size is 512MB, if the data block size is 64MB, the document misregistration amount of the first blocks of data piece is 0 so, the document misregistration amount of the second blocks of data piece is 64, the document misregistration amount of the 3rd blocks of data piece is 128, and the rest may be inferred.Directly do not conduct interviews during user accesses data, but conduct interviews with document misregistration amount and data length with data block, the 128MB of user side access file～256MB part for example, promptly the document misregistration amount is next 2 data blocks of 128.
Step 202, metadata server node selects the data block address of node of respective numbers to send to this user side according to default initial copy number.
Wherein, the initial copy number is kept in the metadata server node in advance, is used to the data block of new establishment to set corresponding copy amount.In addition, when the data block node is selected, can select according to factors such as the handling property of the free space of data block node, data block node or data block node positions, to reach best system resource utilization efficient.In addition, unavailable in order to prevent all data blocks copy that causes owing to exchange fault or rack power failure, usually, do not select to make a plurality of data block copies of same data block be positioned at same rack or with the data block node of same switchboard direct connection.
Particularly, the data block address of node that user side receives has a plurality of, the diverse location of the data block copy that corresponding respectively difference will be preserved.User side can directly be saved in data block copy in above-mentioned each data block node; Also can a data block copy be saved in the data block node, by this data block node these data be saved in other corresponding data block nodes according to the piece copy replication again according to above-mentioned address.
By the described method of present embodiment, user side can be set the copy adjustment information when creating data block copy, makes user side need not to send the copy adjustment information to metadata server node once more, thereby has made things convenient for user's operation.
Metadata server node embodiment 1 of the present invention
Present embodiment provides the metadata server node in a kind of distributed file system, and as shown in Figure 4, this metadata server node 10 comprises metadata processing module 11 and replica management module 12, and its course of work is as follows:
The copy adjustment information of first processing sub, the 111 data query piece copies in the metadata processing module 11 particularly, can be searched the copy adjustment information that is stored in advance in this metadata processing module 11.When the copy adjustment of setting in this copy adjustment information reached constantly, first processing sub 111 sent copy adjustment instruction according to adjusting number with the corresponding copy of this copy adjustment information in this copy adjustment information to replica management module 12; In the replica management module 12 first managed the preservation position of submodule 121 according to the data block copy of the copy adjustment Instruction Selection respective numbers that comes from metadata processing module 11, and data block is saved in the corresponding data block node.Particularly, can select the preservation position of data block copy according to factors such as data block node free space, data block node processing performance, data block node positions.
By the described metadata server node of present embodiment, metadata server node can be adjusted according to the copy adjustment moment that comprises in the copy adjustment information and the several copy amounts to each data block copy of copy adjustment.Make and more copy amount to be set data block very long to the response time or that access frequency is high, to improve the aggregate bandwidth of these data of user capture; And, shorten when the response time of data block copy, or access frequency reduces copy amount, so that leave memory space and input output band width for other data block copy when descending.Thereby in the availability and reliability that guarantee data block, improved the utilization ratio of system resource.
Metadata server node embodiment 2 of the present invention
Present embodiment provides another kind of metadata server node on the basis of the foregoing description 1, as shown in Figure 5, this metadata server node 10 also comprises interface module 13 except comprising metadata processing module 11 and replica management module 12, its course of work is as follows:
Then, copy adjustment information by first processing sub, the 111 data query piece copies of metadata processing module 11, when the copy adjustment of setting in this copy adjustment information reaches constantly, copy adjustment number according to constantly corresponding with this copy adjustment in this copy adjustment information sends copy adjustment instruction to replica management module 12; First of replica management module 12 is managed the preservation position of submodule 121 according to the data block copy of this copy adjustment Instruction Selection respective numbers, and data block copy is saved in the corresponding data block node.
By the described metadata server node of present embodiment, user side can pass through interface module 13, when creating data block, directly sets the copy adjustment information of this piece.Thereby make user side to adjust the number of copies of data block, improved the controllability of system, satisfied user's demand according to the needs of oneself.
Metadata server node embodiment 3 of the present invention
Present embodiment provides another kind of metadata server node on the basis of the foregoing description 1 or 2, as shown in Figure 6, this metadata server node 10 also comprises heartbeat monitor module 14 except comprising metadata processing module 11, replica management module 12 and interface module 13.
Need to prove that herein though represented embodiment 2 described interface modules 13 in Fig. 6 of present embodiment, those skilled in the art should be understood that whether exist interface module 13 not influence the correlation function of the heartbeat module 14 in the present embodiment.
By the described metadata server node of present embodiment, carry out heartbeat monitor by 14 pairs of data block nodes of heartbeat monitor module, can be when the data block node be unavailable, make the copy of setting in the copy amount of data block copy and the copy adjustment information adjust number and be consistent, thereby further improved the reliability of system.
It should be noted that at last: above embodiment only in order to technical scheme of the present invention to be described, is not intended to limit; Although with reference to previous embodiment the present invention is had been described in detail, those of ordinary skill in the art is to be understood that: it still can be made amendment to the technical scheme that aforementioned each embodiment put down in writing, and perhaps part technical characterictic wherein is equal to replacement; And these modifications or replacement do not make the essence of appropriate technical solution break away from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (12)
1. data block copy amount regulation method is characterized in that comprising:
Metadata server node is inquired about the copy adjustment information of a data block copy;
When the copy adjustment of setting in the described copy adjustment information reaches constantly, according to the constantly corresponding copy adjustment of this copy adjustment is several the copy amount that is kept at the described data block copy in the data block node being adjusted in the described copy adjustment information.
2. data block copy amount regulation method according to claim 1 is characterized in that metadata server node also comprises before inquiring about the copy adjustment information of a data block copy:
Metadata server node is preserved described copy adjustment information after receiving and coming from the copy adjustment information of user side; Described copy adjustment information comprises the copy adjustment moment and adjusts number with the constantly corresponding copy of this copy adjustment.
3. data block copy amount regulation method according to claim 2 is characterized in that described metadata server node receives described copy adjustment information and comprises:
Receive the data block that comes from user side and create instruction, described data block is created the copy adjustment information that includes in the instruction at data block copy to be created.
4. data block copy amount regulation method according to claim 3 is characterized in that described metadata server node also comprises after receiving described data block establishment instruction:
Select the data block address of node of respective numbers to send to described user side according to default initial copy number;
The data block copy that described user side will be created according to the described address that receives is saved in the corresponding data block node.
5. data block copy amount regulation method according to claim 3 is characterized in that described metadata server node also comprises after receiving described data block establishment instruction:
Select a data block address of node to send to described user side;
Described user side is according to described address, with a described data block copy be saved in described address corresponding data block node in;
Described data block node according to default initial copy number with this data block copy copying and saving in other data block nodes.
6. data block copy amount regulation method according to claim 1 is characterized in that described metadata server node also comprises before inquiring about the copy adjustment information of a described data block copy: user side replaces with copy adjustment information at a data block copy with default copy adjustment information.
7. according to the described arbitrary data block copy amount regulation method of claim 1-5, it is characterized in that being set with a plurality of copy adjustment moment and copy adjustment number at a data block copy in the described copy adjustment information, wherein each copy adjustment number average is constantly corresponding with a copy adjustment.
8. data block copy amount regulation method according to claim 7, adjustment also comprises afterwards to it is characterized in that finishing once to the copy amount of described data block by described metadata server node:
When the described copy adjustment of the next one does not reach constantly, the state of the data block node of preserving described data block copy is carried out heartbeat monitor;
When monitoring described data block node when unavailable, adjust several copy amounts according to the copy in the described copy adjustment information once more and adjust described data block copy.
9. data block copy amount regulation method according to claim 1 is characterized in that also comprising: by user side described copy adjustment information is upgraded.
10. a metadata server node is characterized in that comprising metadata processing module and replica management module, wherein:
The metadata processing module comprises first processing sub, be used to inquire about the copy adjustment information of a data block copy, when the copy adjustment of setting in the described copy adjustment information reaches constantly, according to adjusting number with the constantly corresponding copy of this copy adjustment in the described copy adjustment information, send copy adjustment instruction to the replica management module;
The replica management module comprises the first management submodule, is used for selecting the preservation position of the data block copy of respective numbers according to the copy adjustment instruction that comes from first processing sub, and data block copy is saved in the corresponding data block node.
11. metadata server node according to claim 10 is characterized in that also comprising:
Interface module is used to receive the copy adjustment information or the data block that come from user side and creates instruction, sends to described metadata processing module; Described data block is created the copy adjustment information that includes in the instruction at data block copy to be created;
Described metadata processing module also comprises:
Second processing sub is used for described copy adjustment information is kept at this metadata server node;
The 3rd processing sub is used for creating instruction according to described data block and sends the address choice instruction to described replica management module;
Described replica management module also comprises:
The second management submodule is used for selecting the data block address of node of respective numbers to send to described user side by described interface module according to default initial copy number.
12., it is characterized in that also comprising according to claim 10 or 11 described metadata server nodes:
The heartbeat monitor module, be used for the state of the data block node of preserving described data block copy is carried out heartbeat monitor, when monitoring described data block node when unavailable, adjust number according to the copy in the described copy adjustment information and send copy adjustment instruction to described replica management module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2007103047141A CN101471845B (en) | 2007-12-27 | 2007-12-27 | Method for adjusting data block counterpart number and metadata server node |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2007103047141A CN101471845B (en) | 2007-12-27 | 2007-12-27 | Method for adjusting data block counterpart number and metadata server node |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101471845A CN101471845A (en) | 2009-07-01 |
| CN101471845B true CN101471845B (en) | 2011-06-15 |
Family
ID=40828982
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2007103047141A Active CN101471845B (en) | 2007-12-27 | 2007-12-27 | Method for adjusting data block counterpart number and metadata server node |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101471845B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| SG183996A1 (en) * | 2010-03-18 | 2012-10-30 | Nuodb Inc | Database management system |
| CN101877725B (en) * | 2010-06-25 | 2014-06-11 | 中兴通讯股份有限公司 | Copy management method and device in distributed storage system |
| CN103095754A (en) * | 2011-10-31 | 2013-05-08 | 台达电子工业股份有限公司 | Distributed document system and back-up position decision method thereof |
| CN102523105B (en) * | 2011-11-30 | 2014-03-26 | 广东电子工业研究院有限公司 | Failure recovery method of data storage and applied data distribution framework thereof |
| US10740323B1 (en) | 2013-03-15 | 2020-08-11 | Nuodb, Inc. | Global uniqueness checking in distributed databases |
| US11176111B2 (en) | 2013-03-15 | 2021-11-16 | Nuodb, Inc. | Distributed database management system with dynamically split B-tree indexes |
| CN105488180B (en) * | 2015-11-30 | 2019-04-26 | 中国建设银行股份有限公司 | A kind of date storage method and system |
| CN107181637B (en) | 2016-03-11 | 2021-01-29 | 华为技术有限公司 | Heartbeat information sending method and device and heartbeat sending node |
| CN108153759B (en) * | 2016-12-05 | 2021-07-09 | 中国移动通信集团公司 | Data transmission method of distributed database, intermediate layer server and system |
| US11573940B2 (en) | 2017-08-15 | 2023-02-07 | Nuodb, Inc. | Index splitting in distributed databases |
| CN112527751B (en) * | 2020-12-16 | 2023-10-31 | 中国联合网络通信集团有限公司 | Data processing method, device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6704836B1 (en) * | 2002-11-13 | 2004-03-09 | Crossroads Systems, Inc. | Method for dynamic control of concurrent extended copy tasks |
| US20040172423A1 (en) * | 2003-02-28 | 2004-09-02 | Microsoft Corporation | Method and system for synchronizing data shared among peer computing devices |
| CN1747346A (en) * | 2004-09-06 | 2006-03-15 | 中兴通讯股份有限公司 | Redundant duplication and duplicator for mutiple data area in telecommunication system |
| CN1815963A (en) * | 2006-03-10 | 2006-08-09 | 清华大学 | Hybrid positioning method for data duplicate in data network system |
-
2007
- 2007-12-27 CN CN2007103047141A patent/CN101471845B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6704836B1 (en) * | 2002-11-13 | 2004-03-09 | Crossroads Systems, Inc. | Method for dynamic control of concurrent extended copy tasks |
| US20040172423A1 (en) * | 2003-02-28 | 2004-09-02 | Microsoft Corporation | Method and system for synchronizing data shared among peer computing devices |
| CN1747346A (en) * | 2004-09-06 | 2006-03-15 | 中兴通讯股份有限公司 | Redundant duplication and duplicator for mutiple data area in telecommunication system |
| CN1815963A (en) * | 2006-03-10 | 2006-08-09 | 清华大学 | Hybrid positioning method for data duplicate in data network system |
Non-Patent Citations (1)
| Title |
|---|
| 杨瑜萍.数据网格环境下基于存储的副本管理策略的研究.《中国优秀硕士学位论文全文数据库，中国学术期刊（光盘版）电子期刊》.2007, * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101471845A (en) | 2009-07-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101471845B (en) | Method for adjusting data block counterpart number and metadata server node | |
| CN101163265B (en) | Distributed database based on multimedia message log inquiring method and system | |
| US7580971B1 (en) | Method and apparatus for efficient SQL processing in an n-tier architecture | |
| CN102395962B (en) | Composite hash and list partitioning of database tables | |
| US7685459B1 (en) | Parallel backup | |
| CN103067433B (en) | A kind of data migration method of distributed memory system, equipment and system | |
| CN105025053A (en) | Distributed file upload method based on cloud storage technology and system | |
| CN107133234A (en) | The method of data cached renewal, apparatus and system | |
| CN102111438B (en) | Method and device for parameter adjustment and distributed computation platform system | |
| CN113377868B (en) | Offline storage system based on distributed KV database | |
| CN107623703B (en) | Synchronization method, device and system for Global Transaction Identifier (GTID) | |
| CN110022338B (en) | File reading method and system, metadata server and user equipment | |
| CN102866995A (en) | File access method for PPN (Peer-to-Peer Network), management method and distributed file system | |
| CN102104617A (en) | Method for storing massive picture data by website operating system | |
| CN102546823A (en) | File storage management system of cloud storage system | |
| CN113168404A (en) | System and method for replicating data in a distributed database system | |
| WO2019045799A1 (en) | Distributed data storage systems | |
| CN110188084A (en) | A kind of distributed file storage system and file memory method | |
| CN107818111A (en) | A kind of method, server and the terminal of cache file data | |
| CN101470733A (en) | Data block copy amount regulation method and distributed file system | |
| CN107943615B (en) | Data processing method and system based on distributed cluster | |
| JP5371656B2 (en) | File search system | |
| CN102982033A (en) | Small documents storage method and system thereof | |
| US20230026912A1 (en) | Systems and methods for storing content items in secondary storage | |
| US7058773B1 (en) | System and method for managing data in a distributed system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |